Camelot¶

In [2]:

from omnidocs.tasks.table_extraction.extractors import CamelotExtractor

from omnidocs.tasks.table_extraction.extractors import CamelotExtractor

c:\Users\laxma\OneDrive\Desktop\CogLab\11-07-2025\Omnidocs\new\Lib\site-packages\transformers\utils\hub.py:111: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
  warnings.warn(

In [3]:

pdf_path = "../../../../tests/table_extraction/assets/table_document.pdf"
result = CamelotExtractor().extract(pdf_path)

pdf_path = "../../../../tests/table_extraction/assets/table_document.pdf" result = CamelotExtractor().extract(pdf_path)

c:\Users\laxma\OneDrive\Desktop\CogLab\11-07-2025\Omnidocs\new\Lib\site-packages\pypdf\_crypt_providers\_cryptography.py:32: CryptographyDeprecationWarning: ARC4 has been moved to cryptography.hazmat.decrepit.ciphers.algorithms.ARC4 and will be removed from cryptography.hazmat.primitives.ciphers.algorithms in 48.0.0.
  from cryptography.hazmat.primitives.ciphers.algorithms import AES, ARC4

INFO     [timestamp]2025-07-31 13:10:29[/] | [logger.name]omnidocs.tasks.table_extraction.extractors.camelot[/] |  
         [function]logging.py:150[/] | [info]extract completed in 1.29s[/]                                         

INFO     [timestamp]2025-07-31 13:10:29[/] | [logger.name]omnidocs.tasks.table_extraction.extractors.camelot[/] |  
         [function]logging.py:150[/] | [info]extract completed in 1.29s[/]                                         

In [4]:

for i, table in enumerate(result.tables):
                print(f"\nTable {i+1}: {table.num_rows} rows x {table.num_cols} columns")
                print(f"Total cells: {len(table.cells)}")

                if table.cells:
                    non_empty_cells = [cell for cell in table.cells if cell.text.strip()]
                    print(f"Non-empty cells: {len(non_empty_cells)}")

                    # Show first few cells
                    for cell in table.cells[:10]:
                        if cell.text.strip():
                            text = cell.text.strip()[:30]
                            print(f"  [{cell.row},{cell.col}]: '{text}'")

for i, table in enumerate(result.tables): print(f"\nTable {i+1}: {table.num_rows} rows x {table.num_cols} columns") print(f"Total cells: {len(table.cells)}") if table.cells: non_empty_cells = [cell for cell in table.cells if cell.text.strip()] print(f"Non-empty cells: {len(non_empty_cells)}") # Show first few cells for cell in table.cells[:10]: if cell.text.strip(): text = cell.text.strip()[:30] print(f" [{cell.row},{cell.col}]: '{text}'")

Table 1: 6 rows x 6 columns
Total cells: 36
Non-empty cells: 31
  [0,0]: 'Disability 
Category'
  [0,1]: 'Participants'
  [0,2]: 'Ballots 
Completed'
  [0,3]: 'Ballots 
Incomplete/ 
Terminat'
  [0,4]: 'Results'